Claude Code setup

One connection. All seven models.

Set up your Agent once, then switch models and reasoning effort in the same session.

Run inOperating system

Prefer to skip manual setup? Ask AI to do it for you.

AI setup prompt

Follow https://siapi.ai/docs/claude-code?model=deepseek-flash&surface=cli&platform=macos to connect my Agent to all SI-API models. Preserve existing settings and ask for my API key when needed.

GLM 5.3 Flash
DeepSeek V4.1 Flash
Kimi K3.1 Pro
Kimi K3.1 Pro HighSpeed
GLM 5.3
MiniMax M3.1 Flash
Qwen3.8 Max

All seven models are in this download. Keep the same configuration when switching models. Get your API key →

1. Prepare your tool and key

Install Claude Code from its official page. Create or copy your SI-API key from /keys.

Official installation guide ↗

Prepare your tool and key

mkdir -p "$HOME/.config/siapi/claude"
# After saving settings.json:
chmod 600 "$HOME/.config/siapi/claude/settings.json"

2. Save the configuration

Download and extract the ZIP. Replace YOUR_SIAPI_API_KEY with your key, then save each file to the path below. Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale.

Configuration location: ~/.config/siapi/claude

settings.json

Save to: ~/.config/siapi/claude/settings.json

Create the dedicated folder, save this file and replace the key placeholder locally. Keep it private.

View or copy configuration

settings.json

Download

{
  "model": "deepseek-flash",
  "modelPicker": {
    "replaceBuiltInOptions": true,
    "options": [
      {
        "model": "glm-5.3-flash",
        "label": "GLM 5.3 Flash",
        "description": "glm-5.3-flash"
      },
      {
        "model": "deepseek-flash",
        "label": "DeepSeek V4.1 Flash",
        "description": "deepseek-flash"
      },
      {
        "model": "kimi-k3.1-pro",
        "label": "Kimi K3.1 Pro",
        "description": "kimi-k3.1-pro"
      },
      {
        "model": "kimi-k3.1-pro-highspeed",
        "label": "Kimi K3.1 Pro HighSpeed",
        "description": "kimi-k3.1-pro-highspeed"
      },
      {
        "model": "glm-5.3",
        "label": "GLM 5.3",
        "description": "glm-5.3"
      },
      {
        "model": "minimax-m3.1",
        "label": "MiniMax M3.1 Flash",
        "description": "minimax-m3.1",
        "behavesAs": "claude-3-5-haiku-20241022"
      },
      {
        "model": "qwen3.8-max",
        "label": "Qwen3.8 Max",
        "description": "qwen3.8-max"
      }
    ]
  },
  "env": {
    "ANTHROPIC_BASE_URL": "https://siapi.ai",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_SIAPI_API_KEY",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-flash",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-flash",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-flash"
  }
}

3. Start your Agent

Start a new session and send a message. The startup model is deepseek-flash.

Start your Agent

CLAUDE_CONFIG_DIR="$HOME/.config/siapi/claude" claude --model deepseek-flash

4. Switch between all models

After setup, choose any model below inside your Agent. The same key and configuration work for all seven models; no new download or connection is needed.

All 7 models in this Agent configuration
Model / API ID	Command / picker path	Thinking settings
GLM 5.3 Flash `glm-5.3-flash`	`/model glm-5.3-flash`	Low / High / Max. Claude Code starts at High; choose /effort max for Max.
DeepSeek V4.1 Flash `deepseek-flash`	`/model deepseek-flash`	Low / High / Max. Claude Code does not reliably send Off to this gateway; use another Agent when you need Off.
Kimi K3.1 Pro `kimi-k3.1-pro`	`/model kimi-k3.1-pro`	Low / High / Max. Claude Code starts at High; choose /effort max for Max.
Kimi K3.1 Pro HighSpeed `kimi-k3.1-pro-highspeed`	`/model kimi-k3.1-pro-highspeed`	Low / High / Max. Claude Code starts at High; choose /effort max for Max.
GLM 5.3 `glm-5.3`	`/model glm-5.3`	Low / High / Max. Claude Code starts at High; choose /effort max for Max.
MiniMax M3.1 Flash `minimax-m3.1`	`/model minimax-m3.1`	Use the model default. This route does not expose custom thinking controls.
Qwen3.8 Max `qwen3.8-max`	`/model qwen3.8-max`	Low / Medium / XHigh. High and Max map to XHigh. Claude Code does not reliably send Off to this gateway.

5. Choose reasoning effort

Send each command separately inside your Agent. On DeepSeek V4.1 Flash, switch from Low to High before your next message.

Inside your Agent

/effort low
/effort high

Terminal · set model and effort at startup

CLAUDE_CONFIG_DIR="$HOME/.config/siapi/claude" claude --model deepseek-flash --effort high

Available effort levels depend on the model; see the table above. MiniMax M3.1 Flash uses its model default.

Effort defaults and saved settings

Start on DeepSeek V4.1 Flash. Choose Low, send a short file-reading task, then choose High and repeat. Check the current setting after each change.

Effort means how much reasoning to request. Kimi K3.1 Pro / HighSpeed, GLM 5.3 and GLM 5.3 Flash offer Low / High / Max with thinking always enabled. Choose Low for shorter reasoning; there is no Off option. Their model default is Max, but a client setting can override it. DeepSeek and Qwen have their own intensity levels listed below.

MiniMax M3.1 Flash uses its default reasoning behavior. MiniMax M3 settings apply to a different model.

Run /effort status to inspect the effective setting. /effort opens the selector; /effort low and /effort high set a level. In current versions these choices can save a per-model default in modelSettings. Use the selector's session-only action or a launch flag such as --effort high for a temporary choice; Max is session-only. Use /effort auto to clear your manual selection; Claude can still choose and send its own effort.

Inside the Agent · send each command separately

/effort status
/effort low
/effort status
/effort high
/effort status

Check /status for managed, project and user settings. A fixed CLAUDE_CODE_EFFORT_LEVEL, a saved modelSettings effort, an older effortLevel setting or a disabled thinking mode can override or conflict with your selection. Keep fixed environment overrides out of the gateway profile when you want interactive control.
In CLI, Kimi K3.1 Pro / HighSpeed and both GLM models accept /effort low, /effort high or /effort max. Claude may offer a broader menu than a backend supports. High / Max on Qwen both select XHigh.

Expected: On DeepSeek V4.1 Flash, the current setting changes from Low to High and back to Low before your next message. Other models follow the controls listed below.

Claude Code effort controls ↗

Check the model and run your first task

Open a project containing README.md. Allow the tool to read it, then send the prompt below. Confirm that it reads the file and returns a summary. To check another model, switch using the table above and repeat this task.

Inside your tool

/status
/model

Send this task in your tool

Use the file-reading tool to read README.md in this project and summarize its purpose in one sentence. Do not modify any files.

Tool-specific notes

Use the origin without /v1; Claude Code appends /v1/messages. Clear conflicting ANTHROPIC_API_KEY credentials in the launching terminal.
Use Claude Code 2.1.257 or later. MiniMax M3.1 uses default reasoning. Opus, Sonnet and Haiku aliases map to DeepSeek Flash; use the seven named rows to switch models.
This guide configures Claude Code CLI. Claude Desktop requires a separate adapter.

Official configuration reference ↗ · Model configuration

Connection not working? · Usage

Agent compatibility — Client versions, tested reasoning fields and known limits.

Download setup instructions